Advertisement

Distance-Intensity for Image Registration

  • Rui Gan
  • Albert C. S. Chung
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3765)

Abstract

In this paper, a novel one-element voxel attribute, namely distance-intensity (DI), is defined for associating spatial information with image intensity for registration tasks. For each voxel in an image, the DI feature encodes spatial information at a global level, and is about the distance of the voxel to its closest object boundary, together with the original intensity information. Without the help of image segmentations, the computation of the DI map is carried out by applying a Poisson process on a vector field that combines both gradient and distance-gradient. Mutual information (MI) is adopted as a similarity measure on the DI feature space. A multi-resolution registration method is then used for aligning multi-modal images. Experimental results show that, as compared with the conventional MI-based method, the proposed method has longer capture ranges at different image resolutions. This leads to more robust registrations. Randomized registration experiments on clinical 3D CT, MR-T1 and MR-T2 datasets demonstrate that the new method gives higher success rates than the traditional MI-based method.

Keywords

Mutual Information Spatial Information Image Registration Image Pair Translational Probe 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Maes, F., Collignon, A., et al.: Multimodality Image Registration by Maximization of Mutual Information. IEEE Trans. Med. Img. 16, 187–198 (1997)CrossRefGoogle Scholar
  2. 2.
    Wells, W., Viola, P., et al.: Multi-Modal Volume Registration by Maximization of Mutual Information. Medical Image Analysis 1, 35–51 (1996)CrossRefGoogle Scholar
  3. 3.
    Penney, G., Weese, J., et al.: A Comparison of Similarity Measures for Use in 2D-3D Medical Image Registration. IEEE Trans. Med. Img. 17, 586–595 (1998)CrossRefGoogle Scholar
  4. 4.
    Pluim, J., et al.: Image Registration by Maximization of Combined Mutual Information and Gradient Information. IEEE Trans. Med. Img. 19, 809–814 (2000)CrossRefGoogle Scholar
  5. 5.
    Pluim, J., Maintz, J., Viergever, M.: Mutual-Information-Based Registration of Medical Images: A Survey. IEEE Trans. Med. Img. 22, 986–1004 (2003)CrossRefGoogle Scholar
  6. 6.
    Rueckert, D., Clarkson, M., et al.: Non-rigid registration using higher-order mutual information. In: Proc. SPIE, Medical Imaging: Image Processing, vol. 3979, pp. 438–447 (2000)Google Scholar
  7. 7.
    Butz, T., Thiran, J.P.: Affine registration with feature space mutual information. In: Niessen, W.J., Viergever, M.A. (eds.) MICCAI 2001. LNCS, vol. 2208, pp. 549–556. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  8. 8.
    Zwillinger, D.: Handbook of Differential Equations, 3rd edn. Academic Press, Boston (1997)Google Scholar
  9. 9.
    Cover, T., et al.: Elements of Information Theory. John Wiley & Sons, Inc., Chichester (1991)Google Scholar
  10. 10.
    Bishop, C.: Neural Networks for Pattern Recognition. Oxford U. Press, Oxford (1995)Google Scholar
  11. 11.
    Press, W., Teukolsky, S., et al.: Numerical Recipes in C, 2nd edn. Cambridge University Press, Cambridge (1992)zbMATHGoogle Scholar
  12. 12.
    Hajnal, J.V., et al.: Medical Image Registration. CRC Press LLC, Boca Raton (2001)CrossRefGoogle Scholar
  13. 13.
    Zhu, Y., Cochoff, S.: Likelihood Maximization Approach to Image Registration. IEEE Trans. Image Processing 11, 1417–1426 (2002)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Rui Gan
    • 1
  • Albert C. S. Chung
    • 1
  1. 1.Lo Kwee-Seong Medical Image Analysis Laboratory, Department of Computer ScienceThe Hong Kong University of Science and TechnologyHong Kong

Personalised recommendations